I saw this post on Matt Birchler's awesome blog and thought I'd join in the fun.

It's interesting to look back on these a few years down the road and see how much/little has changed.

? Mail Client: Apple Mail
? Mail Server: Fastmail
? Notes: Apple Notes
✅ To-Do: Apple Reminders
? Photo Shooting: Apple Camera
? Photo Management: Apple Photos
? Calendar: Fantastical
? Cloud File Storage: Dropbox
? RSS: Reeder
??‍♂️ Contacts: Apple Contacts
? Browser: Safari
? Chat: Slack
? Bookmarks: Pinboard
? Read It Later: Instapaper
? Word Processing: Google Docs
? Spreadsheets: Google Sheets
? Presentations: Google Slides
? News: AP News (once a week or so)
? Music: Plexamp
? Podcasts: Pocketcasts
? Password Management: 1Password
? First game I play each morning: Retro Bowl
? Podcast editing: Logic Pro X
?️ Video editing: Final Cut Pro X
? Code Editor: Visual Studio Code
? Application launcher: Alfred

I first learned Kubernetes ("k8s" for short) in 2018, when my manager sat me down and said "Cloudflare is migrating to Kubernetes, and you're handling our team's migration." This was slightly terrifying to me, because I was a good programmer and a mediocre engineer. I knew how to write code, but I didn't know how to deploy it, or monitor it in production. My computer science degree had taught me all about algorithms, data structures, type systems and operating systems. It had not taught me about containers, or ElasticSearch, or Kubernetes. I don't think I even wrote a single YAML file in my entire degree. I was scared of ops. I was terrified of Kubernetes.

Eventually I made it through and migrated all the Cloudflare Tunnel infrastructure from Marathon to Kubernetes. I didn't enjoy it, and I was way over my deadline, but I did learn a lot. Now it's 2022, and I'm leading a small team of engineers, some of whom have never used Kubernetes before. So I've found myself explaining Kubernetes to them. They seemed to find it helpful, so I thought I'd write it down and share it with the rest of you.

I immediately identified with this post after the author mentioned he was terrified of Kubernetes, because insert Chris Pratt meme here.

This post not only made the point of Kubernetes abundantly clear, it also was unveiled in such a clever and delightful way whereby each problem unveils a slightly more complex way to utilize Kubernetes.

I saved my company half a million dollars in about five minutes. This is more money than I've made for my employers over the course of my entire career because this industry is a sham. I clicked about five buttons.

Oof, this is a very good read that hits pretty close to home. I’ve seen stuff like this in several organizations I’ve worked with.

I wonder why it’s so prevalant?

Embeddings are a really neat trick that often come wrapped in a pile of intimidating jargon.

If you can make it through that jargon, they unlock powerful and exciting techniques that can be applied to all sorts of interesting problems.

I gave a talk about embeddings at PyBay 2023. This article represents an improved version of that talk, which should stand alone even without watching the video.

If you’re not yet familiar with embeddings I hope to give you everything you need to get started applying them to real-world problems.

The YouTube video near the beginning of the article is a great way to consume this content.

The basics of it is this: let’s assume you have a blog with thousands of posts.

If you were to take a blog post and run it through an embedding model, the model would turn that blog post into a list of gibberish floating point numbers. (Seriously, it’s gibberish… nobody knows what these numbers actually mean.)

As you run additional posts through the model, you’ll get additional numbers, and these numbers will all mean something. (Again, we don’t know what.)

The thing is, if you were to take these gibberish values and plot them on a graph with X, Y, and Z coordinates, you’d start to see clumps of values next to each other.

These clumps would represent blog posts that are somehow related to each other.

Again, nobody knows why this works… it just does.

This principle is the underpinnings of virtually all LLM development that’s taken place over the past ten years.

What’s mind blowing is depending on the embedding model you use, you aren’t limited to a graph with 3 dimensions. Some of them use tens of thousands of dimensions.

If you are at all interested in working with large language models, you should take 38 minutes and read this post (or watch the video). Not only did it help me understand the concept better, it also is filled with real-world use cases where this can be applied.

Grandpa loved craft. He didn't put it that way but other people did. My dad said grandpa was a craftsman. I didn’t understand what this meant until one day when we were visiting. We sat down at a restaurant table and it wobbled. We ignored it. But Grandpa dropped as quickly and efficiently as a seal, vanishing underneath the table to fix the cheap, badly-screwed leg with a coin for a screwdriver.

He fixed things often and silently. Grandpa just cared about things working. He had an instinct for not just broken things but soon to be broken things. He would point out risky work, bad decision making in the form of shoddy materials or shifting angles. He was offended by the trace measures left in the world that signified short-term planning. So I learned that this too had something to do with craft. He had a visual vocabulary that amazed me. I think about how he could see these details. He saw choices and constraints and tensions and frictions where I just saw chairs. He saw effort where most people just saw end products.

I’ve got a few posts in mind that I’ll get cracking on soon about my recent malaice and regression towards a mid-life crisis, but this post helped me keep one thing in perspective.

As someone commented on Lobsters, caring is at the root of a craft. How else could you possibly spend your life?

So, if there’s one thing we can praise Spirit Halloween for, it’s maybe not their great urban design elements or place making chops, but just for making it as transparent as possible that this kind of built environment simply isn’t built for long term success.

And instead of trying to build more of it, maybe we should be moving a lot more aggressively to retro fit what we already have.

’But,’ you say, ‘premature optimisation is the root of all evil! Duplication is better than the wrong abstraction! Don’t be an architecture astronaut!’

The developers I’m thinking about already know of all those takes and have internalised them long ago. They know that sometimes ‘good enough’ is the right choice given the constraints of a project. They know that sometimes you need to cut scope to stay on-track. They know that sometimes it’s better to wait to learn more about a domain before rearchitecting a system. And yet in spite of those constraints their output remains golden. These are hard working motherf*ckers whose diligence and perseverance put other devs to shame.

Other devs… like me.

Sometimes, I just CBF.

ChatGPT is not a total panacea, and it doesn’t negate the skill and intelligence required to be a great developer. There are significant benefits to reap from much of traditional programming education.

But this objection is missing the point. People who couldn’t build anything at all can now build things that work. And the tool that enables this is just getting started. In five years, what will novice developers be able to achieve? 

A heck of a lot. 

See, now this is the sort of insight that would’ve played well in a TEDx speech.

So yes, the same jokers who want to show you how to get rich quick with the latest fad are drawn to this year’s trendiest technology, just like they were to crypto and just like they will be to whatever comes next. All I would suggest is that you look back on the history of Birchtree where I absolutely roasted crypto for a year before it just felt mean to beat a clearly dying horse, and recognize that the people who are enthusiastic about LLMs aren’t just fad-chasing hype men.

As we approach the sixth month of debate over this topic, what’s interesting to me is not the details of quiet quitting, or even the question of how widespread the phenomenon actually is, but our collective reaction to its provocations: we’re simultaneously baffled and enthusiastic. To understand this complicated reality, it helps to adopt a generational lens.

Though quiet quitting has gathered diverse adherents, its core energy comes from knowledge workers who are members of Generation Z (born between 1997 and 2012). This is reflected in the movement’s emergence on TikTok, and in the survey data.

Indeed, a look backward reveals that knowledge workers in every previous generation seem to have experienced a similar pattern of work crisis followed by reconceptualization.

It’s probably no surprise to readers of this site that I am a Cal Newport fan, but I really appreciate his summary of the quiet quitting movement.

The interesting part of this article is how he discusses how each generation views employment. It appears every generation since WWII has a similar crisis.